Accurate prediction of treatment response and selection of optimal treatments remain challenging in epilepsy management. With no reliable surrogate biomarkers for treatment response, the current process of selecting an antiseizure medication remains largely a trial-and-error approach. Other non-pharmacological treatment options, such as epilepsy surgery, are viable alternatives for patients with drug-resistant epilepsy. Statistical and machine learning techniques have been used to predict seizure outcomes associated with antiseizure medications and epilepsy surgery. Recent breakthroughs in deep learning have unveiled new pathways and opportunities, potentially revolutionising personalised treatment selection in health care. In this Review, we explore a broad range of studies that have used various statistical and machine learning methodologies, with particular emphasis on state-of-the-art deep learning techniques to predict the outcomes of both pharmaceutical and surgical treatments for epilepsy. We also review potential future research trajectories and address the inherent challenges of incorporating machine learning into the clinical management of epilepsy.
Purpose Tendon transfers and nerve transfers are two techniques available for reconstruction of elbow extension, grip, pinch, and release after spinal cord injury. This systematic review was aimed at assessing and comparing the strength outcomes of tendon and nerve transfers for functional reconstruction of the upper extremity to better guide surgical discussion. Methods This review was registered with PROSPERO ID: CRD42024595503 and followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Embase, Scopus, and MEDLINE were queried for citations that presented strength outcomes for patients having undergone tendon and/or nerve transfers to restore upper-extremity function after a spinal cord injury. Weighted averages were used to report patient demographic data. A pooled estimate of strength outcomes was completed for the brachialis-to-anterior interosseous nerve transfer using a random-effects model. Results Five hundred and ninety-four citations were screened for 51 included studies with a total of 959 patients who were, on average, 31.8 years old (range, 5−76). For elbow extension reconstruction, strength of M3 or greater was reported in 68% of patients who underwent nerve transfers, 79% of patients who underwent a biceps-to-triceps tendon transfer, and 70% of patients who underwent a deltoid-to-triceps transfer. The pooled proportion of patients achieving M3 or better strength after a brachialis-to-anterior interosseous nerve transfer was 0.5 (0.31−0.7), with better outcomes in younger patients. For the supinator-to-posterior interosseous nerve transfer, 78% of patients reported achieving M3 strength or better. Conclusions There is no gold standard for the functional reconstruction of the upper extremity after a spinal cord injury. The choice of procedure(s) remains patient-specific. Several options are available to surgeons treating tetraplegia, and patients have achieved considerable strength recovery from both nerve and tendon transfers. Current evidence demonstrates poor outcomes after brachialis-to-anterior interosseous nerve transfers. More homogeneous follow-up protocols are needed for strength measurement and patient-reported outcome measures for both nerve and tendon transfers. Type of study/level of evidence Therapeutic III.
REM sleep behavior disorder (RBD) is a well-established prodromal marker of α-synucleinopathies, including Parkinson’s disease, dementia with Lewy bodies, and multiple system atrophy. Over 80
Chronic pancreatitis is a progressive inflammatory disorder marked by irreversible parenchymal injury, fibrosis, and multifactorial pain. Therapeutic endoscopy plays a central role in managing obstructive phenotypes and selected complications. This review synthesizes contemporary evidence on endoscopic management of pancreatic duct stones, main pancreatic duct strictures, benign biliary strictures (BBS), pancreatic duct leaks, pancreatic pseudocysts, and endoscopic ultrasound–guided celiac plexus block, addressing the role of endoscopy. A narrative review was performed, evaluating pain relief, ductal decompression, quality of life, adverse events, and reintervention across ERCP-based therapies, extracorporeal shock wave lithotripsy, pancreatoscopy-guided electrohydraulic or laser lithotripsy, and endoscopic management of pancreatic fluid collections and ductal leaks, and endoscopic ultrasound-guided pain interventions. In painful obstructive chronic pancreatitis, targeted endotherapy can provide symptom relief; however, randomized trials generally favor surgery drainage procedures and/or pancreatic resection over endoscopy for sustained pain control, ductal decompression, and physical quality of life, with comparable safety. ERCP alone is appropriate for small pancreatic duct stones, whereas larger stones are managed with extracorporeal shock wave lithotripsy or pancreatoscopy-guided electrohydraulic or laser lithotripsy to achieve ductal clearance. Main PD strictures are managed with dilation and stenting, with single large-caliber plastic stents preferred; routine use of fully covered self-expandable metal stents is discouraged due to higher adverse events. For chronic pancreatitis-associated BBS, fully covered metal and multiple plastic stents demonstrate similar long-term efficacy, with metal stents reducing procedural burden. Symptomatic PPCs are optimally managed endoscopically based on anatomy and ductal communication. EUS-CPB provides short-term analgesia for refractory pain. Endoscopic therapy is integral to multidisciplinary CP management, offering effective, anatomy-driven interventions, while surgery remains preferred for durable pain control in selected patients.
Risk assessment models (RAM) use predictive algorithms to support physicians in personalizing care. For example, a RAM to determine the risk of venous thromboembolism (VTE-RAM) in hospitalized patients offered treatment recommendations that physicians adhered to at varying rates. We sought to investigate which factors influenced physician adherence to prophylaxis recommendations from a VTE-RAM implemented in an inpatient setting. We assessed adherence to treatment recommendations for a VTE-RAM in the inpatient setting using both survey and real-world data sources. Inclusion criteria included being a hospitalist or resident in the inpatient setting, using a VTE-RAM at least 50 times, and having complete data from both sources available. Variation in treatment adherence from the two data sources was compared, and physicians were inductively segmented into high- and low-adherence groups. Seven possible factors influencing adherence were identified using prior research and prioritized using best–worst scaling (BWS). Results were stratified by adherence group, and differences in priorities were tested using Wald tests. We obtained data for 188 physicians, most of whom (56
